Target recognition, identification, and tracking using real and synthetic IR imagery

H. Tim A. Pentecost; Andrew M. Rogoyski; Douglas R. McCann; Andrew J. Maurice

doi:10.1117/12.243492

27 June 1996 Target recognition, identification, and tracking using real and synthetic IR imagery

H. Tim A. Pentecost, Andrew M. Rogoyski, Douglas R. McCann, Andrew J. Maurice

Proceedings Volume 2744, Infrared Technology and Applications XXII; (1996) https://doi.org/10.1117/12.243492
Event: Aerospace/Defense Sensing and Controls, 1996, Orlando, FL, United States

Abstract

In the development of automatic target detection (ATD) and automatic target recognition/identification (ATR/I) systems, the issue of image data is commonly given inadequate consideration. All too often a poorly managed collection of real data, or unrealistic synthetic data is used during development, resulting in a loss of performance when used in the field with imagery having different characteristics. Some of the most promising approaches to ATD and ATR/I, such as neural networks, are particularly susceptible to this problem due to their direct dependence on the training data. This paper highlights the issues involved, with reference to a generic detection and classification approach and to the use of real and synthetic infra-red imagery at the Defence Research Agency at Fort Halstead in the United Kingdom.

Citation Download Citation

H. Tim A. Pentecost, Andrew M. Rogoyski, Douglas R. McCann, and Andrew J. Maurice "Target recognition, identification, and tracking using real and synthetic IR imagery", Proc. SPIE 2744, Infrared Technology and Applications XXII, (27 June 1996); https://doi.org/10.1117/12.243492

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available